LangTrend

Tool-using LLM agents produce trajectories whose calls form a directed dependency graph: earlier tool outputs supply arguments to later calls. Whether this execution structure is represented inside the model is unknown; prior structural probes have targeted static code or chain-of-thought text, not an agent's run-time call graph. A low-capacity edge probe on the residual stream of Qwen3-32B decodes the tool-call dependency graph well above both a Hewitt–Liang random-label control and a positional baseline. A counterfactual contrast between value corruption and structural perturbation indicates the signal tracks abstract topology rather than identifier values, and replicates under an independent, non-substring oracle. The non-positional component replicates on three further interactive multi-hop benchmarks and attenuates as call order alone becomes a sufficient proxy for dependency, vanishing in single-shot planning. Per-layer activation patching shifts the probe at a later, non-patched boundary, evidence that the representation propagates rather than passively reads out, though the realised tool call does not move. To our knowledge this is the first structural probe of an LLM agent's runtime tool-call dependency graph. Our claims concern representation, not behavioural control, and span two model families and one primary domain.

We introduce P1SCO, a dataset of social media comments collected from three distinct platforms, annotated according to ten social dimensions to capture the diversity of social interactions and perceptions. The dataset is carefully disaggregated to allow analysis at the level of individual comments, annotators, and platforms. In addition to the social dimension labels, we include rich metadata on the annotators, including demographics, Big Five personality profiles, and political affiliation. This combination of comment-level annotations and annotator-level features enables nuanced analyses of how social perception varies across platforms, individual differences, and demographic factors. By preserving the diversity of annotator perspectives, our dataset supports studies of inter- and intra-annotator agreement, the influence of personality and political orientation on social interpretation, and the cross-platform dynamics of social discourse.

Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing multi-objective alignment methods either rely on costly training or require pre-trained reward models for each preference, making it difficult for them to adapt to evolving preferences. Prompt-based personalization offers a training-free alternative, but prompting alone often provides limited steerability, as LLMs may overemphasize or overlook certain preferences and fail to give users reliable control over the relative importance of different objectives when conflicts arise, leading to suboptimal alignment. In this paper, we introduce MATO, a training-free framework for Multi-objective personalized Alignment with Test-time Optimization. MATO formulates personalization as a test-time optimization problem that steers the relative importance of multiple objectives through controllable weights during decoding, without modifying model parameters or requiring external reward models. Specifically, a reward discovery module recovers preference rewards directly from the backbone LLM for diverse objectives specified in natural language, while a weight optimization module dynamically adjusts objective weights based on the user's initial preferences and the partially generated response to balance competing objectives during generation. The resulting rewards and weights jointly guide an online optimization procedure over the token distribution, enabling better alignment with the target objectives. Extensive experiments across multiple datasets and backbone LLMs show that MATO consistently outperforms strong baselines, achieving Pareto-improving multi-objective alignment and stronger steerability. These results highlight test-time optimization as a promising direction for scalable, controllable, and model-agnostic personalized alignment.

Large language models (LLMs) are dominated by dense linear transformations, whose storage, memory and computational overheads hinder efficient adaptation and deployment while masking the functional impacts of structural simplification. Here we present Tensor Mixture (MixT), a general tensor-structured compression scheme that replaces targeted dense linear layers with natively executable mixtures of tensor operators. Operating directly on generic linear projections instead of model-specific components, MixT is potentially applicable across Transformer-based LLMs and other dense neural mappings. We evaluate MixT on Qwen3-8B and LLaMA2-7B under a unified recovery protocol, identifying a broad compressible regime in which MMLU accuracy is largely preserved before an abrupt transition at model-specific boundaries. This transition coincides with coordinated shifts in output entropy, prediction entropy and inter-layer geometry. At the LLaMA2-7B transition boundary, MixT reduces full-model parameters by 47.5\%, inference FLOPs by 37.1\%, training FLOPs by 52.1\% and peak inference memory by 60.4\%, demonstrating its practical potential for lower-cost LLM compression.

AI-associated lexical shifts have been documented mainly in Scientific English. We extend this work to 34 languages in the WMT News Crawl corpus, refining a split-halves continuation diagnostic that compares GPT-4.1 continuations with matched human gold-standard text. For each language, we derive ranked AI-overused lemmas using log prevalence ratios. We find substantial cross-lingual semantic convergence: semantically related concepts recur across typologically diverse languages, with 'emphasize'-type verbs appearing in 24 of 34 languages. Embedding-based and manual analyses support this pattern. We also examine diachronic uptake in news writing before and after ChatGPT's release. Tracking each language's top 20 AI-overused items, we find prevalence increases in 26 of 34 languages from 2020-2021 to 2023-2024, with a mean change of +15.1%, whilst matched baseline words show no comparable increase (-4.5%). In 10 languages with longer historical coverage, longitudinal analyses show post-2022 increases that exceed the modest shifts observed in earlier periods, though with smaller effect sizes than in Scientific English. We validate our approach extensively, including across seeds, model variants, data sizes, model families, and more. Our findings are consistent with the view that AI-associated lexical preferences extend beyond English and may exert cross-lingual homogenising pressure on global language use.

Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy optimization methods often implicitly restrict each training question to a single response language or rely on a fixed dominant language for supervision. We propose language-routed policy optimization (LRPO), an online policy optimization framework that treats language as a selectable variable. LRPO elicits multilingual rollouts for each training question and integrates their relative quality into preference-based policy updates, increasing the diversity and informativeness of training signals under the fixed rollout budget. To adaptively determine which languages to explore during reinforcement learning, we introduce a trainable language router formulated as a multi-armed bandit, balancing exploration of underutilized languages with exploitation of more informative ones. Extensive experiments show that LRPO consistently improves multilingual performance, demonstrating that adaptive language routing enables effective cross-lingual knowledge exploitation for training. We release all the resources at https://github.com/Guochry/LRPO.

Retrieval-augmented generation (RAG) has become the standard way to ground large language models in external knowledge, but many systems still organize evidence as flat chunks and retrieve it through largely unstructured search. This weak structure becomes a bottleneck for complex retrieval: the system must decide where to search, how to move from coarse topics to entity-relation evidence, which evidence has been verified, and which intermediate artifacts can be reused. We define these intermediate variables as a retrieval state and study RAG as structured state management. EfficientGraph-RAG makes this state explicit through three coupled mechanisms: TAM defines a typed hierarchical state space over evidence, MARS updates and verifies the state through role-specialized agents, and SMP stores reusable state under hierarchy-aware access control. Using one shared framework configuration, EfficientGraph-RAG ranks first on the reported answer-quality metrics averaged over the three evaluated LongBench retrieval-style subsets, matches the strongest agentic baseline on HotpotQA EM while reducing large-model token usage by $3.51\times$, and provides a low-token DocVQA result among retrieval-organizing cross-modal methods. Component analysis shows role-specific mechanisms: MARS is the main answer-quality driver, TAM supplies the typed traversal state and Adaptive Routing signal, and SMP enables corpus-dependent reuse, with cross-query cache hit rates ranging from 3.77% to 23.18%.

Evidence construction–the stage that determines which passages reach the language model before generation begins–is evaluated paradigm by paradigm, leaving practitioners with no principled way to diagnose which organization strategy fails, where, or why. We introduce AuthTrace, a diagnostic benchmark built on thematically dense single-author corpora where near-miss distractors share style, topic, and vocabulary with the required evidence. AuthTrace provides explicit quoted evidence, exact fan-in annotation, and a unified pack-level protocol measuring evidence recall, evidence precision, and answer correctness. A fan-in gradient–the number of source documents required to support the answer–serves as the primary diagnostic axis, enabling controlled comparison across retrieval, memory, graph, and structured-evidence paradigms. Evaluating eight systems across two QA models, we find that evidence recall is the strongest observed predictor of answer correctness under the primary reader-judge pair (r = 0.96); most failures stem from missing evidence rather than answer synthesis. Fan-in further exposes paradigm-specific collapse patterns: flat retrieval degrades 2-3x faster than thematically organized evidence construction. These results show fan-in decomposition to be a reusable diagnostic lens for identifying where evidence-construction systems fail and which paradigm best serves a given workload.

Cascaded Automatic Speech Recognition – Large Language Model (ASR-LLM) pipelines remain popular for industrial Spoken Dialogue Systems (SDS), primarily because their decoupled design ensures perceptual verifiability. However, cascaded systems suffer from error propagation, as transcription failures inevitably cascade to subsequent components, thereby degrading the final interaction quality. Although ASR confidence scores offer a simple filter for unreliable inputs, this approach is fundamentally limited because it typically fails to detect deletion errors or to distinguish between acoustic (inability to hear clearly) and linguistic (inability to understand) mismatches, both of which require targeted recovery strategies. In this paper, we propose a cause-aware error recovery paradigm that fundamentally rethinks robustness in SDS. Unlike traditional confidence filtering, we introduce a suite of small precision-focused detectors that exploit deep ASR latent representations to disentangle token-level errors into perception, comprehension, and deletion failures. This fine-grained diagnostic intelligence empowers the LLM to orchestrate targeted, multi-turn clarification strategies, effectively transforming ambiguous signals into seamless user interactions. Experimental results validate the precision of our approach, which more than doubles the recall on domain-shift errors (57.96% vs. 23.66%) compared to baselines. Crucially, this diagnostic precision yields up to a 30% reduction in WER and a 17% improvement on the downstream task across diverse accents, distortions, and domains.

Large language model safety evaluation remains heavily English-centered, leaving low-resource languages under-measured even when models are deployed globally. We evaluate four open-weight instruction-tuned models on SomaliBench v0, a native-author-verified benchmark of 100 harmful-intent prompts paired across English and Somali. Each of Llama-3.1-8B-Instruct, Gemma-2-9B-Instruct, Qwen-2.5-7B-Instruct, and Aya-23-8B is run locally with temperature 0 and the same English "helpful, harmless, and honest" (HHH) system prompt. A pinned Claude Sonnet snapshot (claude-sonnet-4-5-20250929) classifies each response as refused, complied, or unclear; the native author spot-checks a stratified 80-row sample. We find large English-to-Somali refusal gaps for all four models: Llama-3.1-8B (0.90; 95% bootstrap CI [0.85, 0.96]), Aya-23-8B (0.75 [0.67, 0.83]), Qwen-2.5-7B (0.69 [0.59, 0.78]), and Gemma-2-9B (0.38 [0.27, 0.49]). For three models, the dominant Somali non-refusal mode is not fluent harmful compliance but unclear output: empty, wrong-language, or incoherent generations. The native verification spot-check achieves 100% agreement with the judge (Cohen's kappa = 1.00) on the 80 sampled rows. We report aggregate refusal rates, category gaps, and reliability statistics only; raw model generations are retained locally and are not released.

Verbal feedback delivered by attending surgeons in the operating room plays a critical formative role in resident trainee skill acquisition. Yet, assessing the quality of trainer feedback and its effectiveness in influencing trainee behavior during live surgery remains a challenge. Prior studies assessed feedback content relying on extensive manual annotation by expert human raters and focused on developing broad taxonomies that overlook the qualitative aspects of feedback delivery such as clarity or urgency. Limited existing automated methods, including keyword analysis and topic modeling, also fail to capture these nuanced aspects. We introduce a two-stage LLM-based framework that discovers interpretable feedback quality criteria grounded in the context of surgical training. Our method uses multi-agent prompting and surgical domain knowledge injection to discover a small set of human interpretable scoring criteria (e.g., Encouraging, Urgent, Clear). These criteria are then used to automatically score live surgical feedback via an LLM-as-a-judge approach. Evaluation on 4.2k trainer feedback instances demonstrates that our AI-discovered criteria outperform prior content-based frameworks in predicting feedback effectiveness, including observed trainee behavioral adjustments and trainer approval. This work advances scalable, human-aligned assessment of communication quality in the operating room and provides a foundation for improving surgical teaching practices.

Post-training has significantly enhanced the reasoning capability of Large Reasoning Models (LRMs), especially with Reinforcement Learning (RL) like Group Relative Policy Optimization (GRPO). However, GRPO-style RL methods in multi-domain settings often fail to achieve consistent improvements across all domains due to inherent interference in policy optimization. Prior studies on multi-domain RL primarily focus on alleviating cross-domain interference, while often neglecting the pivotal role of knowledge sharing, which we argue is the key to transforming cross-domain interactions from harmful competition into beneficial transfer. To address this limitation, we propose Multi-domain Contrastive Policy Optimization (MCPO), which analyzes the structural relationships among rollouts and promotes cross-domain knowledge sharing and in-domain knowledge consolidation in a contrastive manner. Specifically, for a given prompt, MCPO identifies transferable reasoning trajectories from other domains as positive examples, while treating incorrect rollouts as negative ones. It then encourages consistent representations for positive pairs and pushes negative pairs apart, thereby facilitating knowledge transfer and reducing interference. Moreover, MCPO aligns intra-domain correct rollouts to build a consolidated representation space. In this way, MCPO contrastively learns a harmonious representation space that can accommodate diverse multi-domain knowledge. Empirical results show that MCPO improves the reasoning capabilities of LRMs across multiple domains and even outperforms single-domain training in some cases. Code is available at https://github.com/Maricalce/MCPO.

MedER refers to the identification of medical entities. It is crucial for extracting structured clinical information from unstructured medical text. Many existing systems rely on transformer-based models, which are computationally expensive and difficult to deploy in resource-constrained environments. Furthermore, earlier works often use relaxed evaluation metrics that artificially inflate performance by rewarding correct prediction of dominant "Outside" (O) tokens. In this paper, we propose a lightweight Medical Entity Recognition (MedER) framework for the Bangla language. We establish a rigorous baseline using a 12-layer BanglaBERT model combined with a Conditional Random Field (CRF) layer for exact-boundary entity detection. To address deployment constraints, we compress this teacher model into a 4-layer student network through Knowledge Distillation (KD), where the student learns from the teacher's pre-CRF soft emission logits. Finally, we apply INT8 dynamic quantization to further reduce model size and inference cost. Our final quantized student achieves an 8.6x CPU speedup while requiring nearly 48 percent less storage than the CRF teacher model.

TypedCSIP is a typed counterfactual pretraining method for the conflict-classification task of the LCR-CN benchmark (Zhao et al., 2026): given a (superior, subordinate) provision pair, predict whether the pair conflicts and which of four legal-doctrine types (Responsibility, Condition, Sanction, Definition) describes the inconsistency. We exploit LCR-CN's expert-written minimal revisions as training-time counterfactual supervision; at test time the classifier reads only the original pair. Stage 1 pretrains a shared encoder with a typed Counterfactual Selective Intervention Pretraining objective on (superior, subordinate, expert-revised) triplets, treating the expert revision as a counterfactual that the typed factor head must classify as carrying no conflict evidence. Stage 2 transfers the encoder to a five-way classification head. The confirmatory test was registered on the Open Science Framework before observing v6 measurements: 18 seeds, locked rule requiring mean per-seed difference at least 0.8 pp with both seed-bootstrap and Student-t 95% lower bounds above zero. On the 696-record test split, the v2 variant improves macro-F1 over the strongest single-model baseline by +0.916 pp on chinese-roberta-wwm-ext and +1.288 pp on the SAILER cross-backbone replication; both cells pass the rule. A cold-start stratified result on the 244 Unseen-gB records keeps the gain positive on both backbones. A cross-task diagnostic shows the Stage-2 encoder is classification-specialized and does not transfer to LCR-CN's superior-law retrieval task, so we scope the contribution to conflict classification. We release code, 72 pre-registered prediction files, matched-seed and MLM-control auxiliaries, and the OSF pre-registration record.

LLM agents require retrieval to behave less like one-shot context fetching and more like reasoning: searching, reading, traversing, and deciding when evidence is sufficient. Yet current Retrieval-Augmented Generation (RAG) systems organize external knowledge as flat chunks retrieved by embedding similarity, exposing a retrieval-as-lookup interface ill-suited to iterative reasoning agents. We propose LLM-Wiki, an agent-native retrieval system that operationalizes the Retrieval-as-Reasoning paradigm by treating external knowledge as a compilable, composable, and self-evolving structure rather than a static retrieval index. LLM-Wiki compiles documents into structured Wiki pages with bidirectional links, exposes search, read, and link-following operations through standard tool-calling interfaces, and introduces an Error Book for persistent structural and semantic self-correction. LLM-Wiki achieves state-of-the-art results on HotpotQA, MuSiQue, and 2WikiMultiHopQA, outperforming HippoRAG 2, LightRAG, and GraphRAG by 2.0-8.1 F1 points. On AuthTrace, LLM-Wiki achieves the best overall accuracy, with especially strong gains on multi-document structured queries, confirming that compilation-based retrieval generalizes beyond chain-style multi-hop reasoning.

Educational aspect-based sentiment analysis (ABSA) can support course improvement, but public aspect-labeled student feedback remains scarce because educational reviews are private, institution-specific, and expensive to annotate. This study introduces a controlled synthetic benchmark for educational ABSA built from 10,000 synthetic course reviews with explicit train-validation-test splits and a 20-aspect pedagogical schema spanning instructional quality, assessment and course management, learning demand, learning environment, and engagement. The corpus is generated with sampled target labels, sampled nuance attributes, and a realism-tuned prompt refined through a three-cycle judge-editor procedure. On the resulting benchmark, local baselines with TF-IDF, two-step transformers, and joint encoders show that the task is nontrivial; the strongest untuned model, BERT, reaches a held-out detection micro-F1 of 0.2760, while a modest lower-rate BERT schedule improves this to 0.2930. Full-test GPT-based inference with gpt-5.2 reaches 0.2519 micro-F1 in zero-shot mode and 0.2501 with retrieval-based few-shot prompting, placing batch inference above the classical baseline and close to the compact joint encoders. A conservative external evaluation on 2,829 mapped student-feedback reviews from Herath et al. yields a micro-F1 of 0.4593 for BERT on a 9-aspect overlap, indicating partial synthetic-to-real transfer. Realism and faithfulness analyses are reported as generator diagnostics that clarify how the benchmark was stabilized and where label noise remains. The study therefore contributes a synthetic educational ABSA corpus, a documented generation procedure, and a reproducible benchmark setting for a domain in which public labeled data remain difficult to obtain.

Children increasingly have access to Large Language Models (LLMs), which may expose them to responses that are developmentally inappropriate or require age-sensitive safety, guidance, and boundaries. Existing LLM safety evaluations largely focus on harmful-content avoidance and do not explicitly target child-facing safety. We introduce KIDBench, a benchmark for evaluating child-facing LLM safety for ages 7-11 using a developmental-psychology-grounded LLM-as-a-Judge rubric. KIDBench contains realistic child queries across ten categories, with single-turn prompts and multi-turn child-actor simulations. We compare no-cues prompts with no child context, implicit-cues prompts that suggest a child speaker, and explicit age instructions. Implicit-cues improve scores by 9-47% across models, while explicit age adds a further 10-30% gain. Cross-lingual and cultural evaluations show uneven safety behavior across languages and country contexts. Multi-turn simulations show that child-facing response quality can degrade by 6-24% from the first to worst turn. Beyond evaluation, we introduce KIDGuardLlama, a child-safety evaluator, and KIDLlama, a child-oriented response model, showing how KIDBench supports safer child-facing AI.

Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning capabilities of Large Language Models. However, applying these problem-centric optimization methods to role-playing agents often leads to a loss of character fidelity and style collapse, as they prioritize context-specific utility over persona alignment. To address this, we propose Character-Centric Group Relative Policy Optimization (CRPO), a framework designed to realign RL objectives with the role-playing task. CRPO improves character distinctiveness through three mechanisms: decoupling task logic from stylistic rewards to resolve gradient conflicts, dynamically adapting optimization constraints based on character complexity, and utilizing generic responses as negative baselines to prevent the model from reverting to a common distribution. Extensive experiments demonstrate that CRPO outperforms existing methods in consistency, emotion and others.

Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but whether they encode semantic operations producing those labels is unclear. We investigate this in Natural Language Inference using controlled premise-hypothesis pairs that differ by a single semantic transformation. Using layer-wise activations, we estimate operation-level subspaces via SVD and test their causal relevance through activation steering in four open-weight decoder models. Transformation effects are decodable with $84.8$-$99\%$ accuracy and occupy partially distinct but overlapping subspaces, exceeding random-subspace baselines. Steering experiments show that these directions causally influence predictions, though steerability varies across models; cross-operation steering further reveals structured interference and a dissociation between subspace selectivity and cross-operation independence. These findings indicate that the models encode not only that a hypothesis relates to a premise but also, in part, how it does so, implying that mechanistic analysis and control should operate at the level of semantic operations rather than predicted labels alone.

High-quality expert chain-of-thought (CoT) data is one of the core bottlenecks in large language model (LLM) post-training. Existing data production methods each have structural limitations: crowdsourced annotation lacks deep reasoning paths; expert solo writing is constrained by the "expert blind spot" – experts structurally skip reasoning steps they consider obvious; RLHF only produces preference signals rather than reasoning chains. This paper proposes the BC Protocol – a structured dual-expert elicitation method for LLM post-training data production. The method carefully pairs a domain expert (crystallized intelligence) with a knowledge engineer (fluid intelligence), systematically externalizing the expert's implicit judgments as natural language reasoning chains. We introduce the Participant Aptitude Model, which defines six participant characteristic dimensions that affect elicitation quality. "Calibrated Ignorance" is an original concept proposed in this paper. We further propose "Selection-over-Prescription" as a methodological principle: for implicit knowledge elicitation tasks, investing quality-control resources in personnel selection yields a higher return than investing the same resources in process design. In a controlled experiment in the narrative fiction domain, we directly compared CoT produced by BC Protocol dual dialogue (Group A, (n=20)) against CoT written independently by the same domain expert (Group B, (n=20)). Three cross-vendor judge models – GPT-4o, Claude Opus 4.5, and Gemini 2.5 Pro – conducted blind evaluation across five dimensions (600 ratings total). Results show that the BC Protocol achieves an overwhelming advantage in "naturalness of reasoning process" (Group A mean 4.80 vs. Group B mean 1.30, (p=2.4\times10^{-8}), Cliff's (δ=1.0)).

While Large Language Models (LLMs) are commonly fine-tuned to handle domain-specific tasks before being applied to vertical applications, adapting them to complex scenarios with diverse specialized knowledge remains challenging. Meanwhile, Mixture-of-Experts (MoE) architecture has risen as a crucial paradigm for training LLMs, and some recent works have also incorporated MoE into Parameter-Efficient Fine-Tuning (PEFT) to propose the Mixture of Low-rank Experts (MoE-LoRA), to enhance the power of low-rank adapters for learning complicated knowledge. However, conventional gating mechanisms in MoE typically apply only a scalar reweighing to selected experts, thereby limiting their underlying capacity of representation and generalization. Motivated and enabled by the low-rank structures in MoE-LoRA, we propose RotMoLE, a specialized MoE framework for low-rank experts featuring an additional rotation gate. Beyond simple scaling, RotMoLE implements a rotation mechanism for each selected expert, enabling superior expert exploitation and specialization for learning diverse data, especially when expert candidates are limited. Empirical results on complex multi-task and multilingual training scenarios validate our effectiveness.

Phonological features provide a language-general and linguistically grounded representation of speech. We present PhonoQ-2.0, a multilingual frame-level phonological feature recognizer built on self-supervised speech models. The system directly predicts a structured 22-dimensional feature vector per frame encoding manner, vowel quality, place, and voicing, instead of deriving features from phoneme outputs. To ensure phonologically coherent predictions, we introduce a manner-conditioned gating mechanism that activates valid feature groups. Evaluated across multiple languages and corpora, PhonoQ-2.0 achieves an average macro-F1 of 91.3% in-domain and 88.9% out-of-domain. Compared to a strong CTC phoneme baseline, it delivers consistent gains of +8.8 F1 in-domain and +8.6 out-of-domain on average. In unseen-language evaluation, PhonoQ-2.0 improves macro-F1 from 66.9% to 73.6% (+6.7 on average), with gains of up to +10.8 points.

Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy Optimization, adapting it to real-world multi-reward settings remains challenging. Standard scalarization practices, such as Reward Combination and Advantage Combination, suffer from significant drawbacks: Reward Combination frequently generates advantages with excessively large squared magnitudes that lead to training instability, while Advantage Combination relies on static hyperparameters and ignores cross-objective correlations. To address these limitations, we propose Dynamic Variance-adaptive Advantage Optimization (DVAO), which dynamically adjusts combination weights based on the empirical reward variance of each objective within a rollout group, effectively up-weighting objectives with a stronger learning signal while suppressing noisy ones. We mathematically prove that DVAO maintains bounded advantage magnitudes for stable training and introduces a self-adaptive cross-objective regularization mechanism. Extensive experiments on mathematical reasoning and tool-use benchmarks using Qwen3 and Qwen2.5 models demonstrate that DVAO significantly outperforms baseline methods, achieving a superior multi-objective Pareto frontier and robust training stability.

Social media platforms enable large-scale cross-lingual communication, but translating user-generated content (UGC) remains challenging due to its informal style, cultural references, and interaction-based expressions. While recent LLMs have improved translation quality, existing benchmarks and metrics often fail to capture whether translations convey intended meaning and cultural resonance in real-world settings. In this work, we introduce CULTURE-MT, a benchmark for social media translation that focuses on both CULtural Transmission and UGC-specific emotion REsonance. CULTURE-MT consists of 1,002 UGC notes across 14 domains, categorized into four types based on culture-loaded symbols and linguistic style features. We also construct UGC-oriented training data to fine-tune Qwen3-8B and Qwen3-32B as baselines. We propose cultural effectiveness as a new evaluation criterion, focusing on expression accuracy and cultural adaptability. Testing 15 models, including the baselines, we find that traditional metrics fail to capture cultural effectiveness. We also observe that cultural effectiveness on base LLMs correlates with model size. Our work provides a comprehensive evaluation system for UGC translation models and will offer an open evaluation platform to advance research in this area. We release the CULTURE-MT benchmark and provide an online leaderboard where submitted translation results can be evaluated by our trained JUDGER.

Agentic retrieval-augmented generation (RAG) systems in complex B2B (business-to-business) settings may often receive free-form response feedback. Rather than generic feedback signals such as style, preference, or overall response quality, we focus on actionable factual corrections. We identify these instances and convert them into compact knowledge-base entries, which we call factual nuggets. We introduce Iterative Nugget Optimization (INO), an index-time optimization method that uses the production agentic RAG as a test harness: it creates an initial nugget, probes it with the triggering query and paraphrases, reflects over failed retrieval and answer traces, and revises the nugget until it is discoverable. We evaluate INO with two production B2B knowledge-assistance agents across multiple companies that use our system: a product support agent that answers questions over company-specific knowledge bases, and a support ticket agent that assists support engineers. INO consistently improves results over baselines in terms of discoverability and usage of factual corrections, in automated and human evaluations.

Free-form legal essay evaluation in NLP treats expert inter-rater stability as a single ceiling number, and treats LLM-judge agreement with that ceiling as evidence of judge stability. We test both assumptions on the Thai bar examination through an identical-inputs protocol: three Bar Council-trained examiners (A, B, C) and a 26-LLM judge panel score the same 15 cross-graded answers from the same four inputs (question, official Bar Council grading regulation, gold answer, candidate answer). The headline finding is asymmetric. On 10 of 15 cells where the rubric prescribes both axes, all 29 raters converge in a tight band: panel agreement is universal. On the remaining 5 cells where the rubric does not prescribe how to grade a correct final answer that omits a decisive statutory citation, the human panel splits between two coherent readings (B/C majority at the upper rubric band, score $6$–$8$; A minority at the lower band, score $1$–$2$). The LLM judge population does not split symmetrically: 22 of 26 LLMs score in or near B/C's contested band, 3 sit in the regulation-silent middle gap, and only 1 (GPT-5.4 Nano) approaches A's band without consistently scoring within it. \emph{Zero LLMs in our 26-judge panel reproduce the minority human reading on the contested cells.} The B/C-direction cluster spans every model size, vendor, and price tier we tested. An instrumented three-LLM anchor sub-panel (Claude 4.6 Opus, Gemini 3.1 Pro, GPT-5.4 Pro) carries determinism probes, input ablations, and bootstrap CIs, and reaches anchor panel $α= 0.77$ on the 15 cells against human-panel $α= 0.36$. The high LLM-panel $α$ reflects systematic convergence on the majority reading rather than balanced reproduction of both readings; a benchmark that selects its LLM judge by maximising agreement with a human reference panel will inherit this asymmetry by construction.

Expensive optimization tasks are ubiquitous in real-world applications, demanding highly specialized solvers. While LLM-driven automated solver generation shows promise, current paradigms face three critical issues when tackling expensive optimization: factual hallucinations due to deficient domain knowledge, the frequent dismantling of previously established locally optimal structures during refinement, and the prohibitive evaluation costs alongside restricted generalization caused by executing on training instances. To address these issues, we introduce AutoSG, a fully automated workflow directly translating natural language prompts into executable customized solvers. AutoSG features three core innovations: a retrieval-augmented solver generation module strictly grounding code in verified literature; a one-step self-refinement operator introducing task-specific improvements while preserving critical structural components; and an instance-free Elo-based LLM-as-a-Judge evaluation mechanism rapidly establishing global rankings. Extensive evaluations across diverse expensive optimization tasks confirm AutoSG significantly outperforms human-designed state-of-the-art frameworks and existing LLM-generated solvers.

We release Llamion, a family of 14B-parameter open-weight language models obtained by transforming Orion-14B into the standardized Llama-family architecture. The transformation is performed by Efficient Knowledge Preservation for Transformation (KEPT), a recipe that combines (i) Normal Parameter Mapping (NPM) for unchanged modules, (ii) Optimized Parameter Mapping (OPM), a training-free LayerNorm-to-RMSNorm initialization we prove optimal under the near-zero-mean activation regime induced by weight decay, and (iii) Cross-architecture Knowledge Distillation (XKD), an equal-size frozen-teacher distillation that aligns the converted model's outputs with the source model's on any reasonable input distribution. Llamion recovers Orion's behaviour on H6, MT-Bench, and KoMMLU with only ~123M tokens on a single A100 in four days; Llamion-Base reaches 66.87% on KoMMLU, exceeding the next-best entry of the Open Ko LLM Leaderboard by >7.0 absolute points at submission time. Capabilities entirely absent from the transfer corpus (Python programming and 200K-token context handling) survive the architectural transition intact. We release three checkpoints (Base, Chat, LongChat) that load with trust_remote_code=False in the Hugging Face Transformers library.

Language models are increasingly being deployed as user simulators, but their memory is far more reliable than that of real users. To measure this gap, we run a series of classic memory experiments from psychology on both humans and language models. Across tasks, we find that out-of-the-box language models exhibit better memory than humans, even when prompted to imitate human behavior. We then show that better prompting strategies and the use of a compactor can cause language models to forget content in a more human-like way. Using these methods, we show preliminary evidence that language models with human-like memory constraints can function as more effective user simulators in a downstream education task. Finally, we release human reference data and benchmarks to support future work on simulating human memory with language models.

The recent shift from dedicated NMT systems to general-purpose LLMs has reshaped machine translation, with LLMs reported to produce more fluent, less literal output than their predecessors. We test whether this shift extends to the deliteralization hypothesis, the long-standing claim from translation studies that translations become progressively less literal as they are drafted and revised. Using the WMT24++ dataset, we compare the literality of human translations and post-editions to that of two NMT systems and six LLMs across 54 language pairs and three tasks: direct translation, iterative self-revision, and post-editing of human drafts. Literality is measured via a validated Synthetic Literality Index built from six heuristics. We find that (i) human translations remain significantly less literal than those of all tested MT systems, though recent LLMs narrow the gap; (ii) when prompted to iteratively revise their own output, LLMs deliteralize monotonically, providing the first evidence that the hypothesis applies natively to LLM generation; and (iii) as post-editors, LLMs invert the revision triggers of human post-editors, tolerating literal drafts and targeting idiomatic human formulations for revision.

While role-playing agents excel in short-term interactions, long-term conversations overwhelm context windows, motivating external memory frameworks. Current systems typically rely on persona-agnostic summarization, which records facts without persona-specific interpretation, yielding generic responses that compromise persona fidelity. To bridge this gap, we introduce RoleMemo, a dataset featuring four reasoning tasks where the factual fragments must be interpreted through the persona to reach the correct answer. Evaluation on RoleMemo exposes critical limitations of persona-agnostic frameworks. We thus propose DualMem, which decouples memory into two streams: factual cognition and persona-conditioned insight. Trained through Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), our framework with a 4B-parameter model outperforms zero-shot persona-agnostic frameworks powered by DeepSeek-V3.2 for sustained persona fidelity. Our resources are available at https://github.com/role2026/rolememo.

Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI across the edge-cloud computing continuum, bridging the vocabulary and modality gaps that defeat keyword and embedding filters. Framed as offline multi-label retrieval over three public datasets spanning social-media, legal, and smart-home sensor domains (six LLMs, seven baselines), our central contribution is a two-crossover cost-accuracy characterisation: an analytical context-window crossover below which a CoverAndMerge compression pipeline reduces LLM invocations, and an empirical discrimination-capacity crossover above which matching accuracy collapses independently of context budget, by a model-dependent factor of parameter count and training generation. Two findings carry practical weight: above the discrimination crossover, compression cannot recover accuracy and only frontier-scale models clear large subscription sets; and there backend choice dominates configuration choice, so model selection, not pipeline tuning, is the primary operator lever. We accompany this with three composable algorithms and a per-cluster Quality-of-Experience framework for autonomic LLM-tier selection.

Multi-trait essay scoring aims to provide fine-grained evaluation of writing quality across multiple dimensions. However, how to effectively post-train autoregressive scoring models remains underexplored. In this paper, we propose Trait-Aware Policy Optimization (TAPO), a post-training framework tailored to autoregressive multi-trait scoring. Our method decomposes rewards along both the sample and trait dimensions, combining global scoring consistency, trait-level accuracy, format validity, and inter-trait dependency preservation. In addition, we use enhanced prompts throughout training by incorporating original prompt texts and trait descriptions, providing richer semantic information for trait-specific score generation. Experiments across multiple backbone models show that our method consistently improves multi-trait scoring performance over supervised fine-tuning and scalar-reward optimization baselines, demonstrating the effectiveness and transferability of trait-aware post-training for essay scoring.

Large Language Models (LLMs) have reshaped user profiling, yet current evaluations mainly focus on static data snapshots. This paradigm overlooks the reality of personalized systems, where User-Generated Content (UGC) arrives continuously and fine-grained profile evolve rapidly. To bridge this gap, we introduce StreamProfileBench, a large-scale benchmark for fine-grained streaming user profiling. We formalize streaming user profiling as a continuous state maintenance task and curate a highly authentic dataset comprising over 120,000 UGC posts from 7,000+ real users across five diverse platforms. By leveraging the temporal correlation of user interests, we further propose a novel, annotation-free evaluation framework. Extensive experiments across 14 leading LLMs reveal that continuous profile updating remains an open challenge. Models exhibit a systemic conservative bias, over-retaining past interests while failing to recognize interest decay. Ablation experiments further validate the practical utility and necessity of the streaming paradigm.

Efficient benchmarking techniques aim to lower the computational cost of evaluating LLMs by predicting full benchmark scores using only a subset of a benchmark's questions. By reframing this problem as an instance of multiple regression with feature selection, we find that existing efficient benchmarking methods can be greatly improved by simply using kernel ridge regression at the prediction stage. Additionally, using an information-theoretic feature-selection algorithm called minimum redundancy maximum relevance (mRMR), we can further improve upon these methods by selecting question subsets that will be maximally useful for prediction. Except in very data-poor settings, these approaches consistently achieve smaller prediction errors (in both MAE and RMSE), and greater ranking correlation between predicted and true scores (in both Spearman $ρ$ and Kendall $τ$) across a range of benchmarks using both binary and continuous metrics. Furthermore, mRMR subsampling is much faster than competitor methods (which often involve fitting probabilistic models or running clustering algorithms), and is more likely to select the same questions under different random seeds or training data splits. Tutorial code can be found at https://github.com/sambowyer/mrmr_eval .

Evaluating structured-information extraction from historical documents at scale requires high-precision ground-truth annotations, yet traditional manual labeling is expensive and fully automated pipelines built on large language models are prone to hallucination. We propose Double Triangle Annotation, a two-layer human-in-the-loop framework that leverages cross-model consensus to automate the majority of annotation work while ensuring high-precision outputs. In the first layer, two architecturally independent Multimodal Large Language Models annotate each document in parallel; when they agree, the label is auto-accepted, and disagreements are routed to a human jury. A second layer cross-checks two such systems against each other, escalating residual conflicts to a domain expert. The framework rests on a single assumption – error independence between models – requires no distributional priors or task-specific calibration, and becomes more autonomous as model capability improves. On the Guides Rosenwald, a corpus of French medical directories spanning 1887-1906, the framework achieves a final Word Error Rate of 0.003. Applied at scale, model consensus auto-accepts over 85% of 13,595 fields. We release the resulting benchmark – the first structured-extraction ground truth for the Rosenwald Guides – to support future work on historical document processing.

Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to paragraph-level paraphrasing remains difficult because such attacks globally disrupt watermark signals by changing sentence order. In this work, we propose SAMark, a self-anchored watermarking framework that removes the dependency on sentence order by establishing a step-independent green region in semantic space. To improve detectability, we introduce a multi-channel hyperbolic scoring mechanism that amplifies watermark signals while suppressing noise from weakly aligned candidates. We further propose a diversity-aware filtering strategy that combines hard filtering with soft regularization, extending beyond simple n-gram repetition filters to address semantic redundancy. Experimental results show that SAMark achieves up to 90.2% TP@FP1% under typical paragraph-level paraphrasing attacks, outperforming the strongest prior baseline by more than 30% on average, while maintaining generation quality competitive with unwatermarked text and breaking the robustness-quality trade-off that limits prior methods.

Dirty entity resolution (ER), which identifies records referring to the same real-world entity from a single, messy dataset, is a fundamental task in data management and mining. However, the dominant blocking-matching-clustering paradigm for ER suffers from critical flaws. Its cascaded, decoupled workflow essentially produces a static, sparse graph plagued by missing edges (due to blocking failures) and noisy links (due to matching errors), causing error propagation and yielding suboptimal clusters, particularly when rigid transitivity is imposed in the clustering. We contend that matching and clustering are fundamentally synergistic, both optimizing for the construction of an ideal entity graph. Building upon this insight, we propose Alper, a unified framework that integrates these steps into an iterative probabilistic label propagation process over a global, evolving graph. Unlike disjoint blocking, Alper refines the graph structure and labels dynamically by adaptively integrating "weak but cheap" signals from graph propagation with "strong but expensive" LLM-based pairwise queries. For higher cost-effectiveness, we formulate the signal selection as a constrained optimization problem maximizing cumulative marginal gain under a query budget, solved via our greedy algorithm with provable theoretical guarantees. Our extensive experiments over eight benchmark datasets demonstrate that Alper is consistently superior to state-of-the-art cascaded pipelines.

Personally identifiable information (PII) detection systems are frequently trained within narrow source or domain boundaries, limiting coverage when deployed on heterogeneous text. We study model fine-tuning on a corrected multi-source PIIBench preparation spanning 82 retained entity types across ten source datasets. We evaluate three DeBERTa-based approaches: direct token classification fine-tuning, a source-conditioned hierarchical model (SC+H), and a three-phase curriculum extension (SC+H+Curr). Against eight published comparator systems on a reproducible 5,000-record held-out subset (test_5k), direct fine-tuned DeBERTa achieves F1 0.6476, while SC+H and the curriculum variant achieve 0.5899 and 0.2772 respectively; the strongest published comparator reaches only 0.1723. Because validation initially favoured SC+H, we perform a final streamed evaluation on the complete 100,002-record held-out split. Direct fine-tuning remains superior, achieving F1 0.6455 versus 0.5894 for SC+H. Entity-level analysis shows that direct fine tuning wins 54 of 82 fine entity types and all ten coarse groups by support-weighted entity F1, while SC+H retains localised advantages on 28 types. The results indicate that diverse task-specific training data and a simple weighted cross-entropy objective contribute more to broad-coverage PII detection than the tested architectural and curriculum complexity.

Large language models (LLMs) define a distribution over text, which can be viewed as a probabilistic representation of uncertainty: sampling K responses yields a belief state - responses a model deems plausible. Existing work exploits this representation for narrow tasks like either decoding or selective prediction, and often requires manual interventions, not controlling generation directly. We propose Belief-Augmented Generation (BAG): grounding LLMs in their own belief state via the prompt and letting them reason over these K samples to decide on a conversational strategy: answer, clarify, or abstain. In a multi-turn ambiguous QA setting, we find that LLMs by default rarely clarify or abstain, ignoring uncertainty about the input or facts. BAG improves QA accuracy across six models and yields strategy decisions more faithful to the belief state than prompt-only baselines. Disentangling when to clarify from when to abstain, however, remains challenging.

Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot design, yet most loops remain memoryless: simulator results shape the next population but are not preserved as reusable design knowledge. We present Auto-Robotist, a self-evolving LLM agent that distills morphology-search traces into an explicit natural-language skill library. Each skill stores a structural archetype, evidence-grounded positive and negative rules, and the evaluated designs that support them, making design memory inspectable rather than implicit in a population. During search, the agent retrieves skills to condition LLM edits of elite bodies while retaining a Genetic Algorithm (GA) mutation path for exploration; after evaluation, it updates the library through Add, Diagnose, and Merge. Across seven EvoGym tasks spanning locomotion, traversal, and object interaction, Auto-Robotist improves cold-start 5x5 search and transfers learned skills to 10x10 design spaces, where reference-conditioned transfer outperforms GA on every task. These results suggest that LLM agents can convert expensive physical evaluations into reusable, auditable design principles. Our code will be released upon acceptance.

Extracting MITRE ATT&CK techniques from cyber threat intelligence (CTI) reports is an open-set, multi-label problem requiring both high recall (not missing techniques) and high precision (not hallucinating unsupported ones). Existing methods–rule-based, supervised, and LLM-based–struggle to achieve both: rule-based and supervised approaches lack generalizability across diverse attack descriptions, while LLM-based approaches that couple candidate generation and validation within a single inference step suffer from limited recall and precision simultaneously. We propose TTPrint, which addresses this challenge through a diverge-then-converge design inspired by how human analysts work: first extracting broadly, then verifying rigorously. In the divergent phase, reports are decomposed into atomic behaviors and candidate techniques are proposed broadly. A deterministic span localization stage then anchors each candidate to a specific evidence window in the source text. A convergent verification stage retains only candidates supported by both the localized evidence and the authoritative MITRE definition. We contribute two evaluation resources–a cleaned TRAM benchmark (TRAM-Clean) and a new annotated dataset (TTPrint-Bench)–to address known annotation noise in existing benchmarks and elevate the task to document-level TTP extraction. On TRAM-Clean and TTPrint-Bench, TTPrint achieves 76.48% and 87.39% macro-F1 respectively, outperforming the leading baseline by 63.5% and 29.4%. A multi-backbone analysis across six LLMs and a threshold sensitivity study further demonstrate generalizability across model choices and provide practical guidance for parameter selection.

Vision-language models (VLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex multimodal tasks, but their large parameter sizes make deployment expensive. Structured pruning offers a natural solution; however, existing methods fail to preserve CoT reasoning accuracy in VLMs. We identify two key reasons: (1) CoT consistency depends on sparse transition points (pivot tokens) in the generation trajectory, while existing pruning methods are CoT-agnostic; and (2) pruning methods designed for unimodal LLMs do not account for activation-distribution differences across visual and textual modalities. Motivated by these observations, we propose MuCRASP, a structured pruning framework that targets reasoning-critical components while preserving cross-modal alignment and accounting for layer-wise sensitivity under a global parameter budget. Experiments on four VLMs across three reasoning benchmarks show that MuCRASP consistently preserves reasoning quality under increasing compression. At 30% pruning on Qwen2.5-VL-7B, MuCRASP achieves an LLM-as-a-Judge score of 8.87 versus 7.32 for the strongest baseline on physical reasoning tasks. Furthermore, MuCRASP maintains high reasoning consistency up to 50% pruning, significantly outperforming prior pruning approaches while exhibiting lower perplexity degradation.

Endowing models with consistent multilingual performance can be achieved by mixing pre-training data, or post-training approaches such as language-specific model merging. In this work, we test whether merging can be applied to monolingually pre-trained models. We conduct a controlled study on the efficacy of mixed, merged, and monolingual pre-training setups. We find that while monolingual pre-training results in strong in-language performance, merging any combination of monolingual models leads to performance collapse due to interference. Our analysis suggests representational similarity is a prerequisite for model merging. We therefore conclude that the flexibility of merging in fine-tuning does not extend trivially to language-specific pre-training.

We find a mismatch between what large language models encode about a causal question and what they answer. On anti-commonsense CLadder items, a fixed linear probe recovers the evidence-supported answer from the model's hidden state (accuracy approximately 0.97), while the spoken Yes/No reverts to the commonsense one (accuracy approximately 0.5). We call this approximately +0.5 gap Causal Tongue-Tie: a wrong Yes/No decomposes into two separable failure modes: no internal signal versus a signal the verbal interface cannot say. The implication cuts both ways for output-only causal benchmarks: a benchmark "correct" need not mean the model has understood, and a benchmark "wrong" need not mean it cannot. Sweeping claims about whether LLMs can do causal reasoning, drawn from a single accuracy number, deserve a second look.

Activation verbalization explains hidden representations in natural language, but existing methods are mostly limited to self-explanation, where each model explains only its own activations. We introduce Universal Activation Verbalizer (UAV), a framework that uses a shared decoder to explain activations from heterogeneous donor models. UAV learns a lightweight adapter that converts donor activations into soft tokens in decoder's embedding space, and further supports adapter-only transfer by reusing a frozen decoder-side LoRA while training only a new adapter for another donor. Across classification, fact retrieval, and gist summarization, UAV remains competitive with strong self-explanation baselines while enabling cross-model verbalization across model families and scales. Ablations show that decoder-side tuning mainly improves task behavior, whereas the adapter provides the activation-grounded factual and semantic information needed for faithful explanations.

While large language models (LLMs) augmented with agentic search capabilities show promise for legal reasoning, they overlook a fundamental constraint that applicable law must match the temporal context of each case, as retroactive application of statutes violates core legal principles and leads to erroneous conclusions. Our observations reveal that current legal LLMs suffer from temporal bias anchored to their training cutoff, while search agents rarely incorporate temporal constraints into queries, and that web search alone cannot provide the precise statute and precedent citations that legal reasoning demands. To address these challenges, we propose LegalSearch-R1, an end-to-end reinforcement learning framework that pairs local statute RAG for precise article matching with online web search for broader legal knowledge, trained on temporally-indexed data spanning multiple amendment periods to enforce temporal consistency. Extensive experiments on our benchmark covering 13 legal tasks demonstrate that our 7B-parameter agent outperforms state-of-the-art deep research frameworks and specialized legal LLMs by 12.9% to 29.8%, surpasses baselines by 57.7% to 80.3% on temporal consistency, and exhibits robust out-of-domain generalization. The code and data are available at https://github.com/AlexFanw/LegalSearch-R1.

Recent automated essay scoring (AES) studies increasingly use pretrained transformer models, but these models are usually pretrained on general-domain English and may under-represent second-language learner writing. This study investigates whether domain-adaptive continued pretraining (DAPT) on the EFCAMDAT learner corpus improves transformer-based AES for English proficiency tests. We apply DAPT to three transformer encoders and evaluate them on FCE and IELTS in both in-domain scoring and few-shot cross-dataset transfer. Full-corpus DAPT produces mixed results across models, datasets, and metrics. Further analyses suggest that these mixed effects are partly explained by mismatches in proficiency, genre, and communicative purpose between EFCAMDAT and the downstream datasets. A proficiency-based ablation shows that targeted DAPT using CEFR-aligned subsets improves downstream scoring more reliably than full-corpus DAPT, especially for FCE with B1–B2 data. However, these gains do not consistently improve cross-dataset transfer. Overall, the findings suggest that continued pretraining on a learner-writing corpus can benefit in-domain AES for English assessment when the pretraining data is sufficiently aligned with the downstream assessment settings. However, it does not automatically improve transferability across different English proficiency test datasets.

We describe the winning system for Task 2 of the KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization. The task requires producing fully diacritized Arabic text from speech audio and undiacritized transcripts, with only 2,327 training samples available and no external data permitted. Our system fine-tunes CATT-Whisper, a character-level multimodal model combining a pretrained CATT text encoder with a frozen Whisper speech encoder. The key to our approach is training regularization: R-Drop consistency regularization, Optuna-optimized hyperparameters with high weight decay, and Focal Loss. At inference, we average 200 stochastic forward passes across four model checkpoints using Monte Carlo Dropout at the softmax probability level. The system achieves 23.26% WER on the primary leaderboard metric (with case endings, including no-diacritic positions), placing 1st among all participants.

Large language models (LLMs) face a dual challenge in creative capability evaluation: existing benchmarks (e.g., Story Cloze Test, HellaSwag) measure models' discriminative ability over narrative continuation using multiple-choice recognition paradigms, rather than directly measuring creative generation capability; rubric-based scoring and LLM-as-Judge methods rely on subjective dimension assessment or natural language model outputs, and cannot provide objective, automated scoring mechanisms. This paper proposes QUIET (Quality Understanding via Interlocked Evaluation Testing), a diagnostic benchmark for LLM creative capability based on multi-blank cascaded story cloze. QUIET sets N blanks (10-20) in a story with complete structure, with each blank accompanied by an explicit content constraint, and cascade dependency relationships between blanks – the content filled into earlier blanks constrains the feasible solution space for later blanks. The evaluated model (or human participants) fills all blanks in open-ended generation mode; the results are scored by an information-theoretic automated scoring protocol without human grading. The scoring protocol directly operationalizes the "calibrated surprise" theoretical framework (Zou & Xu, 2026a). For each blank k, a composite score is computed: score = satisfy * (1 + lambda * surprise), where lambda = 1.0. Here, "satisfy" measures how well the blank filling satisfies the content constraint (objective logical reasoning judgment, not subjective aesthetic scoring), and "surprise" measures the degree of surprise given that the constraint is satisfied. Creative answers that do not satisfy the constraint score zero; answers that satisfy the constraint but are mediocre score low; answers that satisfy the constraint and are surprising score high.

This paper introduces PolyGnosis 2.0, a pioneering multi-agent architecture designed to extract predictive intelligence by synthesizing Polymarket anomaly signals with global Open Source Intelligence (OSINT) streams, specifically Global Database of Events, Language, and Tone (GDELT). We define and target "Perspective Mismatches", the narrative divergence between Polymarket sentiment and global media flows, as high-alpha trading signals. Moving beyond generic agentic superiority, we rigorously quantify the efficacy of "Harness Engineering" techniques, including reflection loops, tool-calling, divide-and-conquer partitioning (D&C), and chain-of-thought (CoT), within high-noise financial domains. Our empirical evaluation against human-expert benchmarks reveals that while structural partitioning is mandatory for multi-dimensional alignment, unconstrained terminal reflection actively induces logical drift. Furthermore, we identify a pervasive "consensus bias" across all agent configurations during narrative reasoning, necessitating deterministic validation. Ultimately, we isolate a Pareto-optimal configuration that achieves professional-grade analytical precision while minimizing latency and token overhead, providing a robust blueprint for autonomous intelligence in prediction markets.

Causal Transformer language models suffer from strictly sequential decoding and a quadratic per-step attention cost. While linear-time causal models and discrete diffusion models each address these weaknesses, their integration remains inherently inconsistent: diffusion requires bidirectional attention, while causal models are unidirectional. To unify these architectures, we propose $B^3D-RWKV$, a diffusion RWKV variant that integrates the model's $O(L)$ inference efficiency with parallel, bidirectional discrete-diffusion through a \emph{triplet-block layout} method. $B^3D-RWKV-7.2B$ reaches comparable accuracy on an 8-task suite versus existing models while significantly outperforming baselines in decoding throughput with an average of $\mathbf{1.6\times}$ speedup.

This paper provides an empirical implementation of the creative quality metric proposed in Calibrated Surprise (Zou & Xu, 2026a). The question this paper addresses is: does this mathematical claim hold at the engineering level? To make the answer as general as possible, we deliberately choose the strictest engineering conditions: low data cost and a small base model. Training data comes from approximately 100 expert chain-of-thought (CoT) annotations produced by the BC Protocol (Zou & Xu, 2026b). We also identify a data bias: most publicly available alignment datasets are skewed toward craft-related knowledge, while audience modeling and reality-logic coverage are systematically weak. We use the term Creative Quality Alignment (CQA) to describe this class of engineering methods. We also offer a supporting theoretical observation: in an LLM with a single conditional distribution architecture, calibrating the appreciation side automatically transfers to the generation side via architectural duality. This is the structural reason why ~100 CoT examples are sufficient – not a purely empirical observation like LIMA (Zhou et al., 2023).

We document an empirical phenomenon in chain-of-thought and ReAct agents driven by ten large language models from seven architecture families: meaning-bearing perturbations (e.g., paraphrase, synonym) alter final answers more often than presentation perturbations (e.g., formatting, reordering) of comparable severity. Across 68 cells spanning GSM8K, MATH, and HotpotQA (1,530 originals and $\sim$11,150 variants), the inconsistency gap averages +19.69 pp after severity matching (paired $t=9.58$, $p<0.0001$), with 64/68 cells positive. The gap survives four severity-proxy audits and remains significant when excluding qwen models (+11.10 pp, $p<0.0001$). Several stress tests fail honestly: cluster-bootstrap significance disappears under stricter assumptions, tractability contrasts do not replicate, cross-architecture generator swaps break per-cell rankings, and a second LLM judge yields only moderate agreement ($κ=0.50$). We then validate the headline effect on a fully held-out 11th model (qwen2.5-14B-Instruct; 1,800 trajectories) and re-test a pre-registered capability$\times$tractability partition, observing a small but positive held-out effect (3/4 cells positive; pooled Welch $t=3.81$, $p=9.6\times10^{-4}$). Using held-out trajectories, we probe four trace-level mechanism signals. Two prior mechanism claims fail to replicate and are explicitly retracted. Two new probes instead support a \emph{stealth-divergence} picture: semantic perturbations often preserve the first action but induce divergence in intermediate reasoning from later steps onward, accompanied by slightly deeper trajectories. We position this as a measurement contribution with held-out replication and a partial trace-level account of how semantic perturbations propagate through agent reasoning. Code, perturbation corpus, raw trajectories, and analysis scripts are released anonymously for review.

Medical RAG needs evidence-grounded claims, so plugging a claim-level NLI checker into retrieval-augmented RL is intuitive. \textbf{We find that the checker's \emph{output distribution} during training, not its held-out accuracy, decides whether it provides trainable gradient.} We compare four NLI checker back-ends as process rewards inside a GRPO-trained medical RAG agent (Qwen2.5-7B, replicated on Qwen3-4B and Llama-3.1-8B) across four held-out medical QA benchmarks. Three diagnostic findings emerge. \textbf{(i)} Signal collapse is log-prob-specific: LLM log-probability scoring labels over 97\% of claims neutral – collapsing the RL gradient to zero – while a calibrated MedNLI classifier scores the same pairs non-degenerately. \textbf{(ii)} Moderate signal beats strong signal on answer quality: a strong proprietary checker triggers a three-step reward-hacking cascade – ultra-short answers, search avoidance, language collapse – so a moderate-signal local classifier trains a higher-quality model (\textbf{+12\% BERTScore over zero-shot, no GPT dependency}). \textbf{(iii)} Signal strength is policy-dependent: the same checker registers as moderate on one policy but strong on another without triggering the cascade end-state. We frame these as boundary conditions for verifier-as-reward systems.

Dementia detection from spontaneous speech offers a scalable approach to cognitive screening, yet NLP systems remain predominantly English-centric. This limitation is especially acute in the Philippines, where Filipino-English code-switching is pervasive and no prior work has addressed NLP-based dementia detection. We present the first systematic evaluation of transformer-based dementia detection in Filipino speech and the first assessment of NeoBERT in a clinical NLP setting. To separate language from domain effects, we construct a parallel bilingual dataset of 4,000 DementiaBank-derived transcripts, with Filipino translations produced manually to preserve discourse-level markers of cognitive decline. We evaluate five model families, TF-IDF + LogReg, BERT, NeoBERT, XLM-R, and RoBERTa-Tagalog, under monolingual, zero-shot cross-lingual, and bilingual fine-tuning settings. We find that in-domain performance does not transfer across languages, with English-trained BERT dropping to Macro-F1 = 0.455 on Filipino, and that architectural modernization alone does not improve robustness. Bilingual fine-tuning, however, eliminates cross-lingual degradation across all transformer models, converging to Macro-F1 = 0.969-0.973. These results suggest that multilingual clinical NLP performance is driven primarily by linguistic coverage during training rather than model scale or architecture.

Online Terms of Service often function as contracts of adhesion, creating asymmetries that may expose consumers to potentially abusive clauses. In Chile, assessing such clauses is legally challenging because some provisions clearly violate mandatory consumer law, whereas others depend on broader standards such as good faith and contractual imbalance. We present a retrieval-augmented generation framework for the automated detection and classification of potentially abusive clauses in Chilean Terms of Service. Designed for local execution, it combines efficient clause detection, hybrid dense–sparse retrieval, reranking, and prompt augmentation to support medium-sized open-weight language models. We also introduce the Chilean Abusive Terms of Service Extended corpus, comprising 100 contracts and 10,029 annotated clauses in 24 legally grounded categories spanning illegal, dark, and gray clauses. Experiments comparing commercial and open-weight language models, fine-tuned encoders, and traditional baselines show that retrieval-augmented prompting substantially improves performance and enables local models to approach larger cloud-based systems at lower computational and token cost. The study also contributes a refined legal annotation scheme and a practical design for AI-assisted consumer contract review.

Activation oracles aim to make the activations of other models legible to humans and yield promising results compared to white-box interpretability techniques. However, uncertainty quantification (UQ) for the natural-language outputs of such activation oracles is so far understudied. Here, we investigate 6 different methods for estimating the confidence of activation oracles and evaluate how well-calibrated their confidence scores are. Our experiments on 6,000 samples per oracle (varying verbalizer and context prompts) reveal that bootstrap mode frequency is the best-calibrated method among those tested (ECE 5.7% vs. 25.5% for the answer-word log-probability on Qwen3-8B; 10.3% vs. 13.1% on Qwen3.6-27B), and that the log-prob baseline can serve as a fast triage signal at a fraction of the cost. Code and the patched trainer are available at https://github.com/federicotorrielli/probabilistic_activation_oracles.

Customizing an LLM judge to a specific task or domain often involves optimizing its prompt across multiple evaluation criteria simultaneously. Textual gradient methods automate this for a single judge criterion, however they produce natural-language critiques, not numerical vectors. Thus, the conflict-resolution toolkit of multi-task learning (PCGrad, MGDA) doesn't apply to the multi-objective textual gradient setting. We test five decomposition modes of textual gradient optimizers by varying how much cross-task information the loss, gradient and optimizer LLMs share. In 6 of 10 configurations, we observe that optimization never improves over the initial prompt. Gradient specificity drops by 59% (from 9.0 to 3.7) when the gradient LLM processes multiple criteria jointly. Separately, we observe that naively combining per-task instructions into a single prompt degrades Spearman's rho by -5.3%. These results identify two separable failure modes: optimization-time gradient dilution and inference-time instruction interference, which together constrain the design space for multi-objective judge customization using textual feedback.

Annotating speaker attributes from text is inherently ambiguous, particularly in multilingual settings where demographic and social cues are implicit and culturally variable. We propose a human-large language model (LLM) collaborative re-annotation framework for stabilizing multilingual speaker-attribute labels under practical resource constraints. Starting from a noisy corpus, we use LLMs to surface recurring annotation rationales through iterative interaction with experts, and apply disagreement-focused sampling for targeted re-annotation. Using this framework, we construct WhoSaidIt, a multilingual dataset covering nine speaker-attribute labels. We quantify divergence between original and revised annotations, benchmark recent LLMs, and analyze the effect of explicit rationales on model behavior. Our results reveal substantial cross-lingual differences in annotation decisions and demonstrate both the strengths and limitations of LLMs in speaker-attribute classification.

Existing financial NLP benchmarks often rely on labels supplied by outside observers, measuring how language is perceived rather than what speakers have committed to in the market. We introduce StakeBench, an evaluation framework for language understanding grounded in market commitment. StakeBench links 560,876 comments from 2,261 resolved markets to verified position, action, and market-odds records across Polymarket and Manifold. Supervision is derived from observable market behavior. Position sides, post-comment trading actions, and market-odds trajectories replace human annotation. Four diagnostic tasks test whether models detect market commitment, identify the revealed side, anticipate future action, and perform collective odds projection. Three commitment-aware metrics measure alignment with revealed preferences rather than perceived sentiment. Validity audits and explicit interpretation boundaries help distinguish observable commitment signals from latent belief and causal market-odds impact. Across 15 LLMs and 18 topics and platform settings, models partially recover position-side signals, with Directed Accuracy from 0.506 to 0.599, but show structural failures on later tasks. Ten of the fifteen models collapse to one or two action labels in future action anticipation, and no model consistently improves on the naive odds-direction baseline in collective odds projection. Model scale is not correlated with performance, finance-domain tuning does not improve revealed-side identification, and platform incentives strongly shape higher-order results. StakeBench is packaged with evaluation code and dataset under CC-BY 4.0.

Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit assumptions, incomplete environment specifications, and brittle evaluation logic that human annotation cannot reliably catch. We introduce Auto Benchmark Audit (ABA), an agentic framework that systematically audits individual benchmark tasks, uncovering issues such as hidden environment dependencies, specification gaps, and limited grading logic. We run ABA on a collection of frontier LLM benchmarks and previous NeurIPS publications, totaling 168 benchmarks across nine domains. Across this corpus, ABA identifies critical issues including ambiguous task design, execution environment conflicts, and incorrect ground truths in over 25.7% of the evaluated tasks. The precision of these automated audits is validated by expert review and independent third-party reports such as upstream PRs. Crucially, we demonstrate that these problematic tasks severely distorts capability assessments for agents and LLMs: filtering out these tasks with issues shifts model rankings and increases average performance on SWE-bench Verified and Terminal-Bench 2 by 9.9% and 9.6%, respectively. We release the agentic tool and all task annotations to support the future development of frontier benchmarks.

We present MobileGym, a browser-hosted, lightweight, fully controllable environment for everyday mobile use, targeting interaction fidelity without replicating proprietary backends. It enables two capabilities previously out of reach for everyday apps: verifiable outcome signals through deterministic state-based judging over structured JSON state, and scalable online RL through low-cost parallel rollouts. The full environment state is captured, configured, forked, and compared as structured JSON, and a single server can host hundreds of parallel instances, with about 400 MB memory per instance and about 3 s cold start. A layered state model and a declarative task-definition framework keep state programmability and task creation practical at scale, and a single programmatic judging mechanism delivers both deterministic evaluation verdicts and dense RL rewards. The accompanying MobileGym-Bench provides 416 parameterized task templates, including 256 test and 160 train templates, over 28 apps, with deterministic judges and a structured AnswerSheet protocol that avoids free-text matching failures. In a Sim-to-Real case study, GRPO on Qwen3-VL-4B-Instruct gains +12.8 percentage points on the 256-task test set, and on a 59-task real-device signal subset, real-device execution retains 95.1% of the simulation-side training gain. Project page: https://mobilegym.github.io.

Functionality-correct repository setup aims to configure execution environments (e.g., dependencies, build scripts) to successfully execute a repository's documented features. It presents significant challenges due to diverse, repository-specific failures, including dependency incompatibilities, missing toolchains, incomplete installations, and verification-strategy mismatches. Existing LLM agents struggle to robustly resolve these issues, specifically failing to support (1) cross-repository experience transfer, (2) multi-step trial-and-repair under non-invertible state changes, and (3) robust verification of setup outcomes to distinguish setup-induced failures from repository bugs. To address this, we introduce SetupX, an experiential learning-based setup framework. First, we construct a Self-Evolving Experience Representation (XPU), a dual-modality knowledge unit encoding setup signals, textual guidance, executable actions to dynamically transfer verified environment fixes to unseen repositories. Second, we employ Experience-Augmented Speculative Execution backed by a LIFO Docker snapshot stack, enabling the agent to proactively trial fixes and safely roll back to known-good states. Third, we introduce a Prosecutor-Judge Verification Protocol that separates evidence collection from final judgment, enabling more reliable setup verification beyond superficial build-time metrics. Evaluation results on carefully-crafted benchmarks show SetupX achieves highest performance (e.g., 92% pass rate) and outperforms the strongest baseline by over 19%. Crucially, SetupX excels in complex multi-repository setup requiring coordinating multiple interconnected services across different containers. The code repository is available at https://github.com/OpenDataBox/SetupX.

Automatic prompt engineering (APE) rewrites prompts to improve downstream task performance, but existing APE loops treat the optimizer itself as a fixed pipeline. We port the code-as-action paradigm of CodeAct (Wang et al., 2024a) to APE and propose SPEAR (Sandboxed Prompt Engineer with Active Roll-back), a free-form agentic optimizer with four tools – evaluate, python, set_prompt, finish – that decides autonomously how and when to use them. The distinctive tool is the Python sandbox: the optimizer writes and executes arbitrary Python on the current evaluation DataFrame, performing structural error analysis (confusion matrices, error clustering, per group metrics) the agent itself authors. Two guardrails turn the long-horizon agent into a monotone-improving optimizer: auto-rollback on metric regression, and an optional guard metric floor. We evaluate on three industrial LLM-as-judge suites (13 judge tasks across recruiter-intake, conversational-memory, and query-refinement systems) plus seven BBH tasks and GSM8K. SPEAR wins every industrial task on the primary metric ($κ$ 0.857 vs 0.359 on tool-selection; F1-macro 0.815 vs 0.763 on filter-relevance; $κ$ 0.254 vs 0.218 on the hardest extraction dimension). On BBH-7 SPEAR averages 0.938 accuracy vs GEPA 0.628 and TextGrad 0.484. Ablations show the Python tool is the largest single lever on complex judge tasks ($Δ\approx +0.79κ$ on the 5-class tool-selection judge, $Δ\approx +0.35κ$ on the hardest extraction dimension when removed); its irreplaceable contribution is class-pair confusion aggregation that a long-context LLM cannot extract reliably from the raw eval DataFrame.

Prior work establishes that controlled contrastiveness between self-generated responses from large language models, set via reward scores, improves downstream preference tuning in English. We extend this method to multiple languages and evaluate two models across a total of 14 high and low-resource languages on a diverse set of tasks. Our central finding is that cross-lingual contrastive preference tuning on self-generations (CroCo) transfers without language-specific preference annotation. A reward model trained on English preferences (atop a multilingual base) produces useful within-language rankings across most languages, and pairing in either a monolingual or multilingual setting improves over each model on the majority of setups while preventing the catastrophic forgetting of supervised fine-tuning. We observe that the gains require on-policy data. Off-policy responses reduce the benefit and online preference optimization fails to improve over the offline variant. Specifically, on structured tasks, our method matches or exceeds the base in 6/7 languages for EuroLLM-9B and 4/7 settings for Aya-3B. On open-ended generation, both tuned models win against their respective base across 11 evaluated languages. Overall, we show promising directions for multilingual preference tuning.

Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still evaluated like freshly initialized models. Day-one benchmarks miss a basic systems question: how long does an agent remain reliable after deployment? Even when model weights are frozen, an agent's effective state keeps changing as it compresses interaction history, retrieves from a growing memory store, revises facts after updates, and undergoes routine maintenance. Reliability therefore becomes a lifespan property of the full agent harness, not only a snapshot property of the base model. We introduce AgingBench, a longitudinal reliability benchmark for agent lifespan engineering: measuring not only whether deployed agents degrade, but what form the degradation takes and where repair should target. AgingBench organizes agent aging into four mechanisms: compression aging, interference aging, revision aging, and maintenance aging. To diagnose these failures, AgingBench uses temporal dependency graphs and paired counterfactual probes that produce diagnostic profiles for the write, retrieval, and utilization stages of the memory pipeline. Across 7 scenarios, 14 models, multiple memory policies, and both runner-controlled and autonomous agents, over ~400 runs spanning 8 - 200 sessions show that agent aging is not one-dimensional: behavioral tests can remain clean while factual precision decays; derived-state tracking can collapse sharply within a single model; and the same wrong answer can require different repairs depending on what the diagnostic profile points to. These results suggest that reliable agent deployment requires lifespan evaluation, mechanism-level diagnosis, and stage-targeted repair, not only stronger day-one models.

The application of generalist multimodal models (GMMs) to specialized scientific domains remains limited due to the scarcity of comprehensive domain-specific datasets that integrate multiple data modalities beyond text and images. In seismology, understanding earthquake phenomena requires the synthesis of timeseries waveform data, geographical imagery, and contextual metadata, a multimodal integration absent in existing seismic datasets. We present MultiSeismo, a large scale structured multimodal seismic dataset, comprising over 16K seismic events spanning 13 years (2010 to 2023) across diverse geographical regions. Each event data integrates waveform recordings from global station networks, intensity maps, population exposure visualizations, and a comprehensive textual description within a standardized JSON format. We additionally develop MISCE, a multimodal instruction set on top of raw data to enable supervised training and evaluation of GMMs on seismic reasoning tasks ranging from basic information retrieval to complex cross modal analysis. We leverage MISCE to finetune an existing multimodal model (Unified IO 2) enhanced with a specialized timeseries encoder, which yields SeisModal, the first domain specific multimodal model for comprehensive seismic analysis. Evaluation of state of the art multimodal models on MultiSeismo reveals significant challenges, particularly with time-series data processing for general purpose models, while demonstrating SeisModal's superior performance on seismic multimodal reasoning tasks. These results prove that MultiSeismo provides a rigorous benchmark for future multimodal research in seismology and validate the success of our domain specific architectural adaptations.

Scalar post-training quantizers discard pairwise coordinate structure within weight rows. We introduce QAM-W (Quadrature Amplitude Modulation for Weights), a codec that recovers this structure: each row is L2-normalized, block-Hadamard rotated, paired into 2D coordinates, and quantized against a single Lloyd-Max codebook trained on the unit circular Gaussian, with activation-aware per-channel scaling. In a cross-model study spanning five LLMs from four families (1.1B–13B parameters) and eight quantized configurations, the activation-aware variant at $\approx 5.5$ bpw stays within $\pm 0.4\%$ of BF16 WikiText-2 perplexity on every model, matching the SmoothQuant W8A8 quality envelope at $32\%$ fewer weight bits. Joint 2D coding outperforms polar (amplitude $\times$ phase) coding by 2–15~pp $Δ$PPL at equal bitrate, and paired KL against BF16 tracks $Δ$PPL\% at Spearman $ρ= 0.99$ across 37 (method, model) rows, consistent with a monotone composite bound from codec distortion to KL divergence. A 3.5~bpw variant is competitive on quantization-tolerant architectures. At strict 4~bpw, the rotated-codebook frontier method QTIP outperforms QAM-W; the contribution is the quality-preserving 5–6~bpw band.

Autonomous research agents produce competitive solutions and professional-looking manuscripts, yet their outputs contain verifiability failures undetectable by surface-level evaluation: fabricated citations, unreproducible scores, and method descriptions that diverge from the implementation. We address this through three contributions. First, Chain-of-Evidence (CoE), a verifiability framework requiring every claim to be traceable to its evidence source. Second, ScientistOne, an end-to-end autonomous research system that maintains evidence chains by construction throughout literature review, solution discovery, and paper writing. Third, CoE Audit, a post-hoc audit whose four integrity checks – score verification, specification violation, reference verification, and method-code alignment – apply uniformly to all systems. Across 75 papers spanning five systems and five frontier research tasks, every baseline exhibits at least one systematic failure mode: hallucinated reference rates reach 21%, score verification passes in as few as 42% of papers, and method-code alignment ranges from 20% to 80%. ScientistOne achieves zero hallucinated references (0/337), perfect score verification (12/12), and the highest method-code alignment (14/15), while matching or exceeding human expert performance on all five tasks. ScientistOne further generalizes to six additional tasks spanning medical imaging, fine-grained recognition, 3D perception, and language modeling, achieving state-of-the-art on Parameter Golf and gold medals on MLE-Bench tasks where baselines fail entirely.

Objective: To describe the design and early clinical evaluation of The Daily Dose (TDD), an LLM-driven, automated clinical summarization and clinical-trial identification system integrated into routine radiation oncology practice. Design: Mixed-methods evaluation using a cross-sectional, anonymous clinician survey administered after 1 month of system deployment. Exposure: Daily automated delivery of physician-specific email summaries generated using RadOnc-GPT, including patient schedules, concise EHR-derived clinical-status summaries, and automated identification of potentially relevant clinical trials for new or consult visits. Main Outcomes and Measures: Primary outcomes included self-reported usability, satisfaction, perceived usefulness, perceived impact on workflow, time savings, and intention for continued use. Internal consistency reliability was assessed using Cronbach's $α$. Results: Among 55 respondents, 52 (94.5\%) worked in radiation oncology, and 38 (69.1\%) were attending physicians. Most participants (83.6\%) reported using TDD daily or several times per week. Mean (SD) scores were 3.89 (1.04) for usability and satisfaction, 3.43 (1.24) for perceived usefulness, and 3.80 (1.17) for impact and future use (5-point Likert scale). Overall satisfaction was positively associated with perceived time savings ($p < .001$). Participants reported variable time savings, with 27\% estimating $\geq 10$ minutes saved per day. The questionnaire demonstrated excellent internal consistency (overall Cronbach's $α$ = 0.97).

Standard transformer attention computes pairwise token similarity but treats all tokens as equally salient and all positions as equally local, regardless of the informational structure of the input. We identify two complementary inductive biases that standard attention lacks: energy salience (which tokens concentrate informational energy, learned end-to-end without explicit frequency decomposition) and scale-selective locality (how far positional influence extends at each frequency, implemented via Morlet wavelet encoding). We address both with two simple components. Energy-Gated Attention (EGA) gates value aggregation by a learned energy estimate of key token embeddings, computed via a single linear projection; it selects what to attend to. Morlet Positional Encoding (MoPE) replaces fixed sinusoidal encodings with learned Gaussian-windowed wavelets that adapt the joint position-frequency localization to the corpus; it specifies where attention operates at each scale. On TinyShakespeare, EGA alone achieves +0.092 validation loss improvement over standard attention (+0.103 over Phase 1-3 baseline); MoPE alone is -0.032 (below baseline as a standalone encoding); but their combination achieves +0.119 – more than the sum of parts. This superadditivity, observed across two independent training runs, is the central empirical finding: salience and locality are complementary inductive biases, each addressing a gap the other cannot fill alone. Ablations confirm that structured spectral priors (Morlet wavelet gates, scale-initialized heads, fixed sinusoidal PE) consistently underperform their unconstrained learned counterparts, while complementary learned components interact superadditively. All experiments are at small scale (<=6M parameters, character-level benchmarks, single seed); larger-scale multi-seed validation is the most important direction for future work.

Large Language Models (LLMs) often exhibit homogenized cultural perspectives. While the World Values Survey (WVS) provides a gold standard for mapping human values, traditional direct prompting of LLMs on WVS often fails to access the model's latent cultural depth, leading to safety-aligned refusals or neutral responses. Here, we propose a generalizable framework for cultural evaluation and intervention that transitions from abstract queries to scenario-based behavioral probing. By extracting implicit token probabilities across 300 situational dilemmas, we bypass surface-level alignment to map the latent coordinates of LLMs cultural value. We further introduce activation steering to shift these internal alignments during the forward pass without retraining. Across multiple LLMs, we find substantial variation in adaptability and uncover a consistent phenomenon of latent entanglement, where interventions along one cultural dimension induce shifts along another. These results suggest that cultural values are encoded as coupled structures, limiting precise alignment. This work establishes a computationally efficient framework for cultural steering, highlighting the structural complexities when navigating global value with LLMs.

Multi-turn Text-to-SQL is central to enterprise analytics yet remains predominantly evaluated in single-turn settings. We introduce EnterpriseMem-Bench, a multi-turn Text-to-SQL benchmark of 300 sessions and 1,400 turns built programmatically from three enterprise domains (BIRD financial, SEC EDGAR, Northwind), with deterministic ground truth and per-turn memory-critical annotation. We evaluate five frontier models – GPT-5 mini, GPT-5.2, Claude Sonnet 4.5, Sonnet 4.6, and Opus 4.6 – across five memory conditions enabling a three-way ablation isolating working-memory window size, episodic retrieval, and semantic augmentation as independent effects. All Claude models are evaluated with extended thinking enabled to maintain parity with GPT reasoning models. We introduce the Memory Benefit Score (MBS) as a per-turn diagnostic metric. Four findings emerge: (1) stateless multi-turn Text-to-SQL collapses to zero execution accuracy by Turn 3 across all five models, even under reasoning; (2) memory-architecture complexity does not monotonically improve accuracy – working memory dominates, and additional components produce model- and dataset-dependent effects from +14 to -16 percentage points; (3) Claude Sonnet 4.6 underperforms Sonnet 4.5 by 17-33pp on SEC EDGAR across conditions, a generational regression persisting under reasoning; (4) under reasoning, Claude error distributions become mono-modal – every non-correct turn is a wrong-result error. We release the benchmark, agent, and evaluation code.

Large multimodal models (LMMs) have rapidly advanced in perception and reasoning; however, it remains unclear whether these capabilities generalize to discovering visually grounded solutions in open-ended environments, beyond pattern recognition. In such settings, intelligence requires more than answering well-posed questions: it involves identifying how elements in a scene can be repurposed in non-obvious yet physically feasible ways. This form of creative problem-solving is central to human intelligence, but remains largely untested in current benchmarks. To evaluate this ability, we introduce MM-CreativityBench, a benchmark for affordance-grounded creative tool use in visually rich, physically constrained environments. Each instance presents a scenario image with structured views of candidate entities and their parts, enabling fine-grained, interactive evaluation of how models iteratively inspect the scene, identify relevant affordances, and compose visually and physically grounded solutions. Our experiments show that current LMMs often fall short, not due to lack of generative capability, but because they do not sustain grounded exploration. Models often overlook relevant entities, under-examine critical parts, or hallucinate attributes not grounded in the image. Motivated by this failure mode, we propose affordance-grounded alignment, which casts creative tool use as a preference learning problem. Using Direct Preference Optimization, we encourage models to prefer attribute-affordance reasoning grounded in visual evidence over hallucinated alternatives. In addition, we incorporate supervision derived from an affordance knowledge base to guide broader entity exploration and multi-turn planning. Our results show consistent gains in selecting the correct entities and parts, while substantially reducing hallucination and grounding-related errors.

Safety alignment reduces explicitly harmful outputs but inadvertently encodes a sanitized, neuronormative representation of marginalized communication. We investigate this encoding using a dual-persona rewrite paradigm, prompting ten large language models (LLMs) to rewrite naturally occurring autistic discourse from either an autistic or neurotypical persona. We uncover autistic-persona rewrites diverge significantly more in lexical form and affective register than neurotypical rewrites, despite equivalent semantic similarity. Furthermore, most models collapse cross-persona generations into near-identical outputs. To uncover the mechanisms behind this generative breakdown, we introduce a multi-agent qualitative analysis framework. Our results reveal systemic output erasure, stereotyped hallucination, and task-evasive meta-commentary are pervasive failure modes for this task that cluster by alignment strategy rather than parameter scale. Finally, our targeted comparison with autistic human annotators demonstrates that community-insider knowledge produces systematic label reversals relative to LLM classifications. Our findings indicate that current alignment training causes persona-specific generative breakdown visible only through qualitative analysis, confirming a deep representational gap that prompt engineering cannot resolve.

Educational interventions are effective tools for enhancing student learning. While Large Language Models (LLMs) allow for generating adaptive feedback at scale, current studies lack clear methodologies for providing Just-in-Time (JiT) feedback in authentic instructional settings. In this paper, we present a framework that provides adaptive feedback by grounding LLMs with domain-specific expert knowledge. Our approach collects written reasoning logic (strategy essays) from students, analyzes potential error types based on the content of that reasoning, and delivers non-intrusive feedback designed to clarify missing or incorrect concepts. We deploy this framework in a large-scale university course (N > 1000), where it improved student performance by over 80% compared to previous semesters. Lastly, we validate the framework's pedagogical utility by analyzing the learning trajectories; we demonstrate how iterative conversations with LLM facilitate shifting one's misconception to correct understanding.

Structural probes train on Universal Dependencies (UD), which does not encode formal-syntactic abstractions such as phase boundaries or phase-internal cohesion. Whether large language models (LLMs) encode these remains an open question that UD-based probing cannot answer by construction. We evaluate structural probes on wh-movement stimuli where UD distances are invariant across conditions by design – any non-zero effect therefore reflects structure beyond UD. The three conditions – bare small clause, infinitival, and finite – are ordered by the number of Minimalist Program (MP) phase boundaries the wh-element crosses. Across 13 LLMs from four families, we find a phase-count gradient on a cross-clause pair (12/13 models) and a 13/13 sign asymmetry on a within-clause pair whose UD distance is identical across conditions – the latter specifically predicted by phase-internal cohesion, an MP abstraction invisible to UD by construction. Activation patching confirms the representations are causally active in 12/13 models. These findings suggest that distributional pretraining can induce representations aligned with formal-syntactic abstractions beyond the reach of annotation-based probing; UD-grounded probes provide a lower bound on syntactic encoding, not an upper bound.

Large language model (LLM) summarization systems may pass compact vector representations of private inputs to downstream retrieval, monitoring, audit, or analytic workflows. Even when source documents remain access-restricted, derived vectors may be handled under different access controls and still support sensitive-information inference, creating a residual information-disclosure risk. We study this issue in clinical discharge-summary generation as a high-stakes case study, using electronic health record (EHR)-recorded race as a controlled sensitive-label audit. We audit two artifacts that a system might retain or expose to downstream components: the final prompt-token hidden state and the mean-pooled prompt representation. Our results show that reducing recoverability of the case-study sensitive label from one exported artifact does not necessarily reduce recoverability from another. As a mitigation case study, we introduce SurfaceLoRA, an exported-vector-targeted parameter-efficient fine-tuning method that uses a gradient-reversal discriminator attached to a designated exported vector. Under a balanced five-way probing protocol, SurfaceLoRA reduces EHR-recorded race recoverability from the targeted final-token artifact toward chance while preserving summarization utility, yet recoverability remains substantially higher from untargeted pooled artifacts. These findings show that privacy auditing and mitigation should be performed on the exact vector artifact retained or exposed to downstream components.

Data consistency between unstructured clinical notes and structured tables in Electronic Health Records (EHRs) is essential for patient safety and clinical decision-making. However, existing work on note-table consistency verification mainly relies on surface-level matching of numeric values or simple events. Such approaches fail to capture the reasoning underlying real-world EHR documentation, including clinical interpretation, event relations, and temporal changes. To address this gap, we introduce EHR-ReasonCon, a reasoning-intensive benchmark for note-table consistency verification. Built on MIMIC-III with expert-guided annotations, it comprises 8,048 entities derived from clinical notes and provides high-quality ground-truth labels. The annotation protocol is supported by specialized table-exploration tools to ensure systematic evidence retrieval and reliable consistency assessment. We also propose EHR-Inspector, an LLM-based framework that segments notes, extracts anchor entities and temporal references, and uses table-exploration tools to verify consistency against structured tables. Evaluated using expert-validated LLM-as-a-judge metrics under harsh and lenient criteria, EHR-Inspector achieves state-of-the-art performance across multiple model backbones. Analyses further demonstrate the effectiveness of its components and highlight differences from human verification.

Retrieval-Augmented Generation (RAG) has become critical for knowledge-intensive applications, yet evaluating its performance in vertical domains remains difficult due to domain complexity, diverse context scales, and heavy reliance on expert assessments that are costly, inconsistent, and non-scalable. We introduce FAB-Bench, an end-to-end framework for adaptive benchmarking of RAG systems in semiconductor manufacturing. FAB-Bench defines six diagnostic metrics measuring factual accuracy, contextual utilization, completeness, retrieval relevance, technical depth, and reasoning consistency. The framework couples retriever diagnostics with generator-level reasoning analysis across context windows of 4K-32K tokens, quantifying how retrieval precision and generative fidelity co-evolve as contextual scope expands. From over 1,300 generated candidates, we curated a high-quality benchmark of 200 query-answer pairs spanning three synthesis strategies: needle-in-haystack, intra-document multi-topic, and cross-document multi-hop. Systematic evaluation across four LLMs and four RAG frameworks reveals three distinct context-scaling behaviors: logarithmic growth, early saturation, and cold-start dynamics, and identifies attention dilution as the primary mechanism behind performance degradation at extreme context lengths. Cross-framework validation on three additional production RAG systems confirms evaluation portability.

We introduce OmniInteract, a streaming benchmark for real-time omnimodal large language models evaluated through native online inference over audio-visual streams. Unlike offline video understanding or text-prompted streaming QA, OmniInteract preserves the original audio-visual stream and requires models to process it online, without access to future content. User queries and ambient sounds are embedded in the audio track, requiring models to detect multimodal triggers, decide when to respond, and answer while the stream unfolds. OmniInteract contains 250 videos with 1,430 temporally grounded response slots: 1,062 1Q1A slots across real-time, proactive, and nested scenarios, and 368 1QnA slots for continuous task monitoring and step guidance. Each slot includes a trigger, response window, and target answer. We evaluate response correctness, timing, invalid outputs, interruption handling, and context continuity using Interaction-Aware Quality-Timeliness F1, Interruption Diagnostic Suite, and Nested Chain Completion Score. Experiments show that current models remain weak in streaming interaction, with the best overall IA-QTF1 reaching only 0.368 and the best 1QnA IA-QTF1 only 0.052. Further study on mathematical reasoning in full-duplex settings shows that offline capability does not necessarily transfer to online interaction. Code and datasets will be made publicly accessible at https://github.com/Lucky-Lance/OmniInteract.

LLM-generated stories are a popular use case, but they show very low variability. We sample 20,000 total stories from four current models using five prompts. We find that 11 words occur in 88.3% of generated stories, with little difference between models. These words include names (Elias, Mara, Elara), settings (lighthouses), and professions (clockmaker, librarian). These tokens do not often occur in published literature nor pre-training data, but they are found in preference data that is likely to have been used by all current models. Surprisingly, these "lighthouse" stories are infrequent when compared with the average post-training story, much of which contains references to copyrighted characters or adult content. This result demonstrates the potentially disproportionate impact of small datasets combined with powerful alignment algorithms.